Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary

By Pinar Duygulu Sahin, Kobus Barnard, João Freitas, D.A. Forsyth. 2002

1,873 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Trevor Darrell
2. Mohit Bansal
3. Andrew Zisserman
4. Li Fei-Fei
5. Bernt Schiele
6. Dacheng Tao
7. Cordelia Schmid
8. Abhinav Kumar Gupta

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Andrew Zisserman
4. Trevor Darrell
5. Xiaogang Wang
6. Jitendra Malik
7. Li Fei-Fei
8. Yi Yang

In Multimodal Learning

1. Mohit Bansal
2. Marcus Rohrbach
3. Devi Parikh
4. Li Fei-Fei
5. Zhe Gan
6. Tamara L. Berg
7. Trevor Darrell
8. Cordelia Schmid

Citations in the corpus

• Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “This includes classical image classification [5, 10], annotation [9, 17], and captioning [24, 23].”
• A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “In particular, standard image annotation datasets used by Makadia et al. (2008); Guillaumin et al. (2009); Rasiwasia and Vasconcelos (2007); Verma and Jawahar (2012) – namely, Corel5K (Duygulu et al., 2002), ESP Game (von Ahn and Dabbish, 2004), and IAPR-TC (Grubinger et al., 2006) – have only two v”
• Using Multiple Segmentations to Discover Objects and their Extent in Image Collections (2006, background): “[6] for a clever joint use of segments and textual annotations).”
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “…(2015) put it, image captioning is a task whose input is static and non-sequential (an image, rather than, say, a video), whereas the output is sequential (a multiword text), in contrast to non-sequential outputs such as object labels (e.g. Duygulu et al., 2002; Ordonez et al., 2016, among others).”
• Deep Convolutional Ranking for Multilabel Image Annotation (2013, methodology): “GIST [27]: We resized each image to 200 × 200 and used three different scales [8, 8, 4] to filter each RGB channel, resulting in 960-dimensional (320 × 3) GIST feature vectors.”
• Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers (2008, methodology): “For evaluation we use a subset of the Corel5k training and test dataset used in [5].”
• Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning (2019, methodology): “Some widely used databases include Corel 5k [16] (including 4,999 images with 260 object categories), ESP Game [17] (including 20,770 images with 268 categories), IAPRTC-12 [18] (including 19,627 images with 291 categories), NUSWIDE [19] (including 270K images with 81 categories), MS COCO [20] (incl”
• Learning to Separate Object Sounds by Watching Unlabeled Video (2018, background): “Early “words and pictures” work used machine translation or topic models to discover the association between objects labeled in an image and the regions that contain them [6, 20].”
• Computing iconic summaries of general visual concepts (2008, background): “Note that recent literature contains much more sophisticated approaches for building joint statistical models of words and images [2, 8 ]. However, these approaches are concerned with the problem of establishing correspondence between individual tags and specific image sub-regions, which is much mo”
• Online Metric Learning for Multi-Label Classification (2020, methodology): “To evaluate the performance of our proposed online metric learning algorithm, we conduct experiments on four benchmark datasets: Corel5k, Enron, Medical and Emotions.”